Neural network based predictive control for nonlinear processes with time-delay

Author

Tan, Yonghong ; De Keyser, Robin

Author_Institution

Dept. of Autom. Control, Ghent Univ., Belgium

Volume

2

fYear

1994

fDate

2-5 Oct 1994

Firstpage

1116

Abstract

This paper presents two control strategies using neural network based predictors to compensate for the influence of time-delay in nonlinear systems. Firstly, a d-step-ahead neural predictor based control method is proposed. Then, a control scheme based on neural Smith predictor is given for large time-delay compensation. A design procedure based on stability analysis is presented. Finally a comparison between the two kinds of neural control is given

Keywords

compensation; control system synthesis; delay systems; neurocontrollers; nonlinear control systems; predictive control; stability; control design; large time-delay compensation; multistep-ahead neural predictor; neural Smith predictor; neural network based predictive control; nonlinear processes; nonlinear systems; stability analysis; time-delay; Automatic control; Control systems; Feedforward neural networks; Multi-layer neural network; Neural networks; Nonlinear control systems; Nonlinear systems; Predictive control; Predictive models; Recurrent neural networks; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on

Conference_Location

San Antonio, TX

Print_ISBN

0-7803-2129-4

Type

conf

DOI

10.1109/ICSMC.1994.399993

Filename

399993